Python · Compiler
ABOUT THE ROLE
Join a healthtech team building a production compiler that turns clinical standards into executable, traceable decision logic. This research-focused role combines experimentation with frontier AI models and engineering work that supports clinical use.
WHAT YOU'LL DO
- Build pipelines to parse clinical documents and transform their content into validated executable modules.
- Design and refine a target representation for clinical guideline logic.
- Evaluate open and closed models, fine-tuning approaches, and constrained decoding techniques.
- Develop benchmarks, datasets, metrics, and adversarial cases to assess clinical fidelity and logical completeness.
- Analyze model errors and use findings to guide experiments and improve the production compiler.
- Build deterministic validators using static analysis, constraint solving, or formal methods to surface ambiguity, contradictions, and missing source information.
- Collaborate with clinicians and company leadership to validate system outputs and guide development.
WHAT WE'RE LOOKING FOR
- At least 3 years of research or industry experience, or final-year PhD or postdoctoral experience.
- Experience shipping production engineering work and ML or NLP systems.
- A bachelor's degree or higher in computer science, machine learning, mathematics, or a related technical field.
- Production-level experience with Python, PyTorch, and the Transformers ecosystem, plus experience in LLM evaluation, training, or prompt engineering.
- Ability to communicate failed experiments and uncertainty clear